INDEX

Explanations

terms related to academic or professional positions and statuses

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑĸÐ½ÑĮ

-0.17

kazy

-0.16

ÑĢÑĥÐ½

-0.14

à¸ı

-0.14

APPER

-0.14

ì¹Ļ

-0.14

 ÎķÎ½

-0.14

-Cs

-0.13

rome

-0.13

verity

-0.13

POSITIVE LOGITS

asma

0.15

DFS

0.15

elder

0.14

arih

0.14

Äįka

0.14

agus

0.13

ãģŁãģ¡ãģ¯

0.13

able

0.13

xic

0.13

Activations Density 0.443%

terms related to academic or professional positions and statuses

No Comments

No Known Activations